Improved Image Segmentation via Cost Minimization of Multiple Hypotheses
Marc Bosch Bosch, Christopher Gifford, Austin Dress, Clare Lau and Jeffrey Skibo
Abstract
Image segmentation is an important component of many image understanding systems. It aims to group pixels in a spatially and perceptually coherent manner. Typically, these algorithms have a collection of parameters that control the degree of over-segmentation produced. It still remains a challenge to properly select such parameters for
human-like perceptual grouping. In this work, we exploit the diversity of segments produced by different choices of parameters. We scan the segmentation parameter space and
generate a collection of image segmentation hypotheses (from highly over-segmented to
under-segmented). These are fed into a cost minimization framework that produces the
final segmentation by selecting segments that: (1) better describe the natural contours of
the image, and (2) are more stable and persistent among all the segmentation hypotheses. We compare our algorithm’s performance with state-of-the-art algorithms, showing that we can achieve improved results.
Session
Spotlights
Files
Paper (PDF)
Video (MP4)
DOI
10.5244/C.31.7
https://dx.doi.org/10.5244/C.31.7
Citation
Marc Bosch Bosch, Christopher Gifford, Austin Dress, Clare Lau and Jeffrey Skibo. Improved Image Segmentation via Cost Minimization of Multiple Hypotheses. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 7.1-7.12. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_7,
title={Improved Image Segmentation via Cost Minimization of Multiple Hypotheses},
author={Marc Bosch Bosch, Christopher Gifford, Austin Dress, Clare Lau and Jeffrey Skibo},
year={2017},
month={September},
pages={7.1-7.12},
articleno={7},
numpages={12},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
doi={10.5244/C.31.7},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.7}
}